tatsu-lab / linguistic_calibrationLinks
Align your LM to express calibrated verbal statements of confidence in its long-form generations.
☆26Updated last year
Alternatives and similar repositories for linguistic_calibration
Users that are interested in linguistic_calibration are comparing it to the libraries listed below
Sorting:
- ☆40Updated last year
- ☆44Updated last year
- General-purpose activation steering library☆78Updated last month
- Augmenting Statistical Models with Natural Language Parameters☆27Updated 9 months ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆60Updated 7 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆72Updated 3 months ago
- Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…☆11Updated 5 months ago
- ☆29Updated last year
- ☆25Updated 2 weeks ago
- Code for the paper "Spectral Editing of Activations for Large Language Model Alignments"☆24Updated 6 months ago
- ☆51Updated last year
- ☆9Updated last year
- ☆49Updated last year
- ☆35Updated 6 months ago
- ☆54Updated 2 years ago
- ☆41Updated 8 months ago
- Learning adapter weights from task descriptions☆19Updated last year
- Lightweight Adapting for Black-Box Large Language Models☆22Updated last year
- Restore safety in fine-tuned language models through task arithmetic☆28Updated last year
- Official code for "Decoding-Time Language Model Alignment with Multiple Objectives".☆24Updated 7 months ago
- Source codes for "Preference-grounded Token-level Guidance for Language Model Fine-tuning" (NeurIPS 2023).☆16Updated 5 months ago
- ☆44Updated 3 months ago
- This repository contains data, code and models for contextual noncompliance.☆23Updated 11 months ago
- ☆35Updated last month
- Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning [ICML 2024]☆17Updated last year
- ☆44Updated 9 months ago
- The code of paper "Toward Optimal LLM Alignments Using Two-Player Games".☆17Updated last year
- ☆95Updated last year
- Self-Supervised Alignment with Mutual Information☆19Updated last year
- ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"☆35Updated 4 months ago